ArticleScientific reports2023
Molecule generation using transformers and policy gradient reinforcement learning.
Article in Scientific reports, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 32 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
32 citing papers in PubMed.
- Multi-objective-conditioned-return-blocks decision transformer: a novel approach for multi-objective de novo drug design.Bioinformatics (Oxford, England) · 2026Article
- PockLigGPT: Pocket-Sequence-Conditioned Molecular Generation with GPTs and RL.Journal of chemical information and modeling · 2026Article
- The impact of reward scalarization and weight scheduling on optimization dynamics in multi-objective molecular design.Journal of cheminformatics · 2026Article
- A survey of transformer and LLM-based architectures, workflows, and systems in drug discovery.Journal of computer-aided molecular design · 2026Review
- Mol-CADiff: text-conditional molecule generation via causality-aware autoregressive diffusion.Nature communications · 2026Article
- EvoDiffMol: evolutionary diffusion framework for 3D molecular design with optimized properties.Journal of cheminformatics · 2026Article
- Chemical neighborhood exploration for substrate discovery in biocatalysis.Proceedings of the National Academy of Sciences of the United States of America · 2026Article
- Novel molecular design via a scaffold-aware transformer with multi-scale attention mechanisms.Journal of cheminformatics · 2026Article
- Uncertainty Calibration in Molecular Machine Learning: Comparing Evidential and Ensemble Approaches.Chemistry (Weinheim an der Bergstrasse, Germany) · 2026Article
- A survey on large language models in biology and chemistry.Experimental & molecular medicine · 2026Review
- Molecular Design with Artificial Intelligence: Progress and Perspectives for Small Molecules.Chemical reviews · 2026Review
- MolVE: An Open-Source Web Platform for Visualizing and Evaluating AI-Designed Molecules to Aid in Prioritization.Journal of chemical information and modeling · 2026Article
- MolOrgGPT:Journal of chemical information and modeling · 2026Article
- Artificial Intelligence for Natural Products Drug Discovery in Neurodegenerative Therapies: A Review.Biomolecules · 2026Review
- Benchmarking Molecular Mutation Operators for Evolutionary Drug Design.International journal of molecular sciences · 2025Article
- MOFGPT: Generative Design of Metal-Organic Frameworks using Language Models.Journal of chemical information and modeling · 2025Article
- Cycle-configuration descriptors: a novel graph-theoretic approach to enhancing molecular inference.Journal of cheminformatics · 2025Article
- Targeted molecular generation with latent reinforcement learning.Scientific reports · 2025Article
- Enhancing Unconditional Molecule Generation via Online Knowledge Distillation of Scaffolds.Molecules (Basel, Switzerland) · 2025Article
- Artificial Intelligence in Natural Product Drug Discovery: Current Applications and Future Perspectives.Journal of medicinal chemistry · 2025Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Generating novel valid molecules is often a difficult task, because the vast chemical space relies on the intuition of experienced chemists. In recent years, deep learning models have helped accelerate this process. These advanced models can also help identify suitable molecules for disease treatment. In this paper, we propose Taiga, a transformer-based architecture for the generation of molecules with desired properties. Using a two-stage approach, we first treat the problem as a language modeling task of predicting the next token, using SMILES strings. Then, we use reinforcement learning to optimize molecular properties such as QED. This approach allows our model to learn the underlying rules of chemistry and more easily optimize for molecules with desired properties. Our evaluation of Taiga, which was performed with multiple datasets and tasks, shows that Taiga is comparable to, or even outperforms, state-of-the-art baselines for molecule optimization, with improvements in the QED ranging from 2 to over 20 percent. The improvement was demonstrated both on datasets containing lead molecules and random molecules. We also show that with its two stages, Taiga is capable of generating molecules with higher biological property scores than the same model without reinforcement learning.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.